查看文章

Attention operators based on 2D image cues (such as color, texture) are well known and discussed extensively in the vision literature but are not ideally suited for robotic applications. In such contexts it is the 3D structure of scene elements that makes them interesting or not. We show how a bottom-up exploration mechanism that selects spaces of interest (SOIs) based on scene elements that pop out from planes is used within a larger architecture for a cognitive system. This mechanism simplifies the object localization as single plane detection, which is however not practical when dealing with real scenes that contains objects with complicated structures (e.g. objects in a multi-layer shelf). Therefore, the key work required for this situation is the multi-plane estimation, which is solved in this paper using Particle Swarm Optimization (PSO).